Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7752. Min Act: -0.0000

Data Index: 989024 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7950. Min Act: -0.0000

Data Index: 654163 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1205927 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7418. Min Act: -0.0000

Data Index: 20000 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7323. Min Act: -0.0000

Data Index: 586366 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7572. Min Act: -0.0000

Data Index: 552280 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7348. Min Act: -0.0000

Data Index: 183196 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7357. Min Act: -0.0000

Data Index: 275985 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6784. Min Act: -0.0000

Data Index: 694977 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6929. Min Act: -0.0000

Data Index: 305626 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6889. Min Act: -0.0000

Data Index: 148384 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7175. Min Act: -0.0000

Data Index: 175567 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6806. Min Act: -0.0000

Data Index: 435973 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6697. Min Act: 0.0000

Data Index: 1206735 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6822. Min Act: -0.0000

Data Index: 519473 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6740. Min Act: -0.0000

Data Index: 688850 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6463. Min Act: -0.0000

Data Index: 427896 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6083. Min Act: -0.0000

Data Index: 805138 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5873. Min Act: -0.0000

Data Index: 253929 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1130480 (C4 (Web Text))

Max Activating Token Index: 740